#include <linux/mmu_notifier.h>
#include <linux/rmap.h>
#include <linux/swap.h>
+#include <linux/shrinker.h>
#include <linux/mm_inline.h>
#include <linux/kthread.h>
#include <linux/khugepaged.h>
#include <linux/freezer.h>
#include <linux/mman.h>
#include <linux/pagemap.h>
+#include <linux/migrate.h>
+
#include <asm/tlb.h>
#include <asm/pgalloc.h>
#include "internal.h"
(1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)|
#endif
(1<<TRANSPARENT_HUGEPAGE_DEFRAG_FLAG)|
- (1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG);
+ (1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG)|
+ (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG);
/* default scan 8*512 pte (or vmas) every 30 second */
static unsigned int khugepaged_pages_to_scan __read_mostly = HPAGE_PMD_NR*8;
/* during fragmentation poll the hugepage allocator once every minute */
static unsigned int khugepaged_alloc_sleep_millisecs __read_mostly = 60000;
static struct task_struct *khugepaged_thread __read_mostly;
-static unsigned long huge_zero_pfn __read_mostly;
static DEFINE_MUTEX(khugepaged_mutex);
static DEFINE_SPINLOCK(khugepaged_mm_lock);
static DECLARE_WAIT_QUEUE_HEAD(khugepaged_wait);
return err;
}
-static int __init init_huge_zero_page(void)
+static atomic_t huge_zero_refcount;
+static unsigned long huge_zero_pfn __read_mostly;
+
+static inline bool is_huge_zero_pfn(unsigned long pfn)
{
- struct page *hpage;
+ unsigned long zero_pfn = ACCESS_ONCE(huge_zero_pfn);
+ return zero_pfn && pfn == zero_pfn;
+}
+
+static inline bool is_huge_zero_pmd(pmd_t pmd)
+{
+ return is_huge_zero_pfn(pmd_pfn(pmd));
+}
- hpage = alloc_pages((GFP_TRANSHUGE | __GFP_ZERO) & ~__GFP_MOVABLE,
+static unsigned long get_huge_zero_page(void)
+{
+ struct page *zero_page;
+retry:
+ if (likely(atomic_inc_not_zero(&huge_zero_refcount)))
+ return ACCESS_ONCE(huge_zero_pfn);
+
+ zero_page = alloc_pages((GFP_TRANSHUGE | __GFP_ZERO) & ~__GFP_MOVABLE,
HPAGE_PMD_ORDER);
- if (!hpage)
- return -ENOMEM;
+ if (!zero_page) {
+ count_vm_event(THP_ZERO_PAGE_ALLOC_FAILED);
+ return 0;
+ }
+ count_vm_event(THP_ZERO_PAGE_ALLOC);
+ preempt_disable();
+ if (cmpxchg(&huge_zero_pfn, 0, page_to_pfn(zero_page))) {
+ preempt_enable();
+ __free_page(zero_page);
+ goto retry;
+ }
- huge_zero_pfn = page_to_pfn(hpage);
- return 0;
+ /* We take additional reference here. It will be put back by shrinker */
+ atomic_set(&huge_zero_refcount, 2);
+ preempt_enable();
+ return ACCESS_ONCE(huge_zero_pfn);
}
-static inline bool is_huge_zero_pfn(unsigned long pfn)
+static void put_huge_zero_page(void)
{
- return pfn == huge_zero_pfn;
+ /*
+ * Counter should never go to zero here. Only shrinker can put
+ * last reference.
+ */
+ BUG_ON(atomic_dec_and_test(&huge_zero_refcount));
}
-static inline bool is_huge_zero_pmd(pmd_t pmd)
+static int shrink_huge_zero_page(struct shrinker *shrink,
+ struct shrink_control *sc)
{
- return is_huge_zero_pfn(pmd_pfn(pmd));
+ if (!sc->nr_to_scan)
+ /* we can free zero page only if last reference remains */
+ return atomic_read(&huge_zero_refcount) == 1 ? HPAGE_PMD_NR : 0;
+
+ if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) {
+ unsigned long zero_pfn = xchg(&huge_zero_pfn, 0);
+ BUG_ON(zero_pfn == 0);
+ __free_page(__pfn_to_page(zero_pfn));
+ }
+
+ return 0;
}
+static struct shrinker huge_zero_page_shrinker = {
+ .shrink = shrink_huge_zero_page,
+ .seeks = DEFAULT_SEEKS,
+};
+
#ifdef CONFIG_SYSFS
static ssize_t double_flag_show(struct kobject *kobj,
static struct kobj_attribute defrag_attr =
__ATTR(defrag, 0644, defrag_show, defrag_store);
+static ssize_t use_zero_page_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ return single_flag_show(kobj, attr, buf,
+ TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG);
+}
+static ssize_t use_zero_page_store(struct kobject *kobj,
+ struct kobj_attribute *attr, const char *buf, size_t count)
+{
+ return single_flag_store(kobj, attr, buf, count,
+ TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG);
+}
+static struct kobj_attribute use_zero_page_attr =
+ __ATTR(use_zero_page, 0644, use_zero_page_show, use_zero_page_store);
#ifdef CONFIG_DEBUG_VM
static ssize_t debug_cow_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
static struct attribute *hugepage_attr[] = {
&enabled_attr.attr,
&defrag_attr.attr,
+ &use_zero_page_attr.attr,
#ifdef CONFIG_DEBUG_VM
&debug_cow_attr.attr,
#endif
*hugepage_kobj = kobject_create_and_add("transparent_hugepage", mm_kobj);
if (unlikely(!*hugepage_kobj)) {
- printk(KERN_ERR "hugepage: failed kobject create\n");
+ printk(KERN_ERR "hugepage: failed to create transparent hugepage kobject\n");
return -ENOMEM;
}
err = sysfs_create_group(*hugepage_kobj, &hugepage_attr_group);
if (err) {
- printk(KERN_ERR "hugepage: failed register hugeage group\n");
+ printk(KERN_ERR "hugepage: failed to register transparent hugepage group\n");
goto delete_obj;
}
err = sysfs_create_group(*hugepage_kobj, &khugepaged_attr_group);
if (err) {
- printk(KERN_ERR "hugepage: failed register hugeage group\n");
+ printk(KERN_ERR "hugepage: failed to register transparent hugepage group\n");
goto remove_hp_group;
}
if (err)
return err;
- err = init_huge_zero_page();
- if (err)
- goto out;
-
err = khugepaged_slab_init();
if (err)
goto out;
goto out;
}
+ register_shrinker(&huge_zero_page_shrinker);
+
/*
* By default disable transparent hugepages on smaller systems,
* where the extra memory used could hurt more than TLB overhead
return 0;
out:
- if (huge_zero_pfn)
- __free_page(pfn_to_page(huge_zero_pfn));
hugepage_exit_sysfs(hugepage_kobj);
return err;
}
}
__setup("transparent_hugepage=", setup_transparent_hugepage);
-static inline pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
+pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
{
if (likely(vma->vm_flags & VM_WRITE))
pmd = pmd_mkwrite(pmd);
}
#endif
-static void set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm,
- struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd)
+static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm,
+ struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd,
+ unsigned long zero_pfn)
{
pmd_t entry;
- entry = pfn_pmd(huge_zero_pfn, vma->vm_page_prot);
+ if (!pmd_none(*pmd))
+ return false;
+ entry = pfn_pmd(zero_pfn, vma->vm_page_prot);
entry = pmd_wrprotect(entry);
entry = pmd_mkhuge(entry);
set_pmd_at(mm, haddr, pmd, entry);
pgtable_trans_huge_deposit(mm, pgtable);
mm->nr_ptes++;
+ return true;
}
int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
return VM_FAULT_OOM;
if (unlikely(khugepaged_enter(vma)))
return VM_FAULT_OOM;
+ if (!(flags & FAULT_FLAG_WRITE) &&
+ transparent_hugepage_use_zero_page()) {
+ pgtable_t pgtable;
+ unsigned long zero_pfn;
+ bool set;
+ pgtable = pte_alloc_one(mm, haddr);
+ if (unlikely(!pgtable))
+ return VM_FAULT_OOM;
+ zero_pfn = get_huge_zero_page();
+ if (unlikely(!zero_pfn)) {
+ pte_free(mm, pgtable);
+ count_vm_event(THP_FAULT_FALLBACK);
+ goto out;
+ }
+ spin_lock(&mm->page_table_lock);
+ set = set_huge_zero_page(pgtable, mm, vma, haddr, pmd,
+ zero_pfn);
+ spin_unlock(&mm->page_table_lock);
+ if (!set) {
+ pte_free(mm, pgtable);
+ put_huge_zero_page();
+ }
+ return 0;
+ }
page = alloc_hugepage_vma(transparent_hugepage_defrag(vma),
vma, haddr, numa_node_id(), 0);
if (unlikely(!page)) {
* run pte_offset_map on the pmd, if an huge pmd could
* materialize from under us from a different thread.
*/
- if (unlikely(__pte_alloc(mm, vma, pmd, address)))
+ if (unlikely(pmd_none(*pmd)) &&
+ unlikely(__pte_alloc(mm, vma, pmd, address)))
return VM_FAULT_OOM;
/* if an huge pmd materialized from under us just retry later */
if (unlikely(pmd_trans_huge(*pmd)))
* a page table.
*/
if (is_huge_zero_pmd(pmd)) {
- set_huge_zero_page(pgtable, dst_mm, vma, addr, dst_pmd);
+ unsigned long zero_pfn;
+ bool set;
+ /*
+ * get_huge_zero_page() will never allocate a new page here,
+ * since we already have a zero page to copy. It just takes a
+ * reference.
+ */
+ zero_pfn = get_huge_zero_page();
+ set = set_huge_zero_page(pgtable, dst_mm, vma, addr, dst_pmd,
+ zero_pfn);
+ BUG_ON(!set); /* unexpected !pmd_none(dst_pmd) */
ret = 0;
goto out_unlock;
}
static int do_huge_pmd_wp_zero_page_fallback(struct mm_struct *mm,
struct vm_area_struct *vma, unsigned long address,
- pmd_t *pmd, unsigned long haddr)
+ pmd_t *pmd, pmd_t orig_pmd, unsigned long haddr)
{
pgtable_t pgtable;
pmd_t _pmd;
mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
spin_lock(&mm->page_table_lock);
+ if (unlikely(!pmd_same(*pmd, orig_pmd)))
+ goto out_free_page;
+
pmdp_clear_flush(vma, haddr, pmd);
/* leave pmd empty until pte is filled */
smp_wmb(); /* make pte visible before pmd */
pmd_populate(mm, pmd, pgtable);
spin_unlock(&mm->page_table_lock);
+ put_huge_zero_page();
inc_mm_counter(mm, MM_ANONPAGES);
mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
ret |= VM_FAULT_WRITE;
out:
return ret;
+out_free_page:
+ spin_unlock(&mm->page_table_lock);
+ mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
+ mem_cgroup_uncharge_page(page);
+ put_page(page);
+ goto out;
}
static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
count_vm_event(THP_FAULT_FALLBACK);
if (is_huge_zero_pmd(orig_pmd)) {
ret = do_huge_pmd_wp_zero_page_fallback(mm, vma,
- address, pmd, haddr);
+ address, pmd, orig_pmd, haddr);
} else {
ret = do_huge_pmd_wp_page_fallback(mm, vma, address,
pmd, orig_pmd, page, haddr);
page_add_new_anon_rmap(new_page, vma, haddr);
set_pmd_at(mm, haddr, pmd, entry);
update_mmu_cache_pmd(vma, address, pmd);
- if (is_huge_zero_pmd(orig_pmd))
+ if (is_huge_zero_pmd(orig_pmd)) {
add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR);
- else {
+ put_huge_zero_page();
+ } else {
VM_BUG_ON(!PageHead(page));
page_remove_rmap(page);
put_page(page);
return page;
}
+/* NUMA hinting page fault entry point for trans huge pmds */
+int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long addr, pmd_t pmd, pmd_t *pmdp)
+{
+ struct page *page;
+ unsigned long haddr = addr & HPAGE_PMD_MASK;
+ int target_nid;
+ int current_nid = -1;
+ bool migrated;
+ bool page_locked = false;
+
+ spin_lock(&mm->page_table_lock);
+ if (unlikely(!pmd_same(pmd, *pmdp)))
+ goto out_unlock;
+
+ page = pmd_page(pmd);
+ get_page(page);
+ current_nid = page_to_nid(page);
+ count_vm_numa_event(NUMA_HINT_FAULTS);
+ if (current_nid == numa_node_id())
+ count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL);
+
+ target_nid = mpol_misplaced(page, vma, haddr);
+ if (target_nid == -1) {
+ put_page(page);
+ goto clear_pmdnuma;
+ }
+
+ /* Acquire the page lock to serialise THP migrations */
+ spin_unlock(&mm->page_table_lock);
+ lock_page(page);
+ page_locked = true;
+
+ /* Confirm the PTE did not while locked */
+ spin_lock(&mm->page_table_lock);
+ if (unlikely(!pmd_same(pmd, *pmdp))) {
+ unlock_page(page);
+ put_page(page);
+ goto out_unlock;
+ }
+ spin_unlock(&mm->page_table_lock);
+
+ /* Migrate the THP to the requested node */
+ migrated = migrate_misplaced_transhuge_page(mm, vma,
+ pmdp, pmd, addr,
+ page, target_nid);
+ if (migrated)
+ current_nid = target_nid;
+ else {
+ spin_lock(&mm->page_table_lock);
+ if (unlikely(!pmd_same(pmd, *pmdp))) {
+ unlock_page(page);
+ goto out_unlock;
+ }
+ goto clear_pmdnuma;
+ }
+
+ task_numa_fault(current_nid, HPAGE_PMD_NR, migrated);
+ return 0;
+
+clear_pmdnuma:
+ pmd = pmd_mknonnuma(pmd);
+ set_pmd_at(mm, haddr, pmdp, pmd);
+ VM_BUG_ON(pmd_numa(*pmdp));
+ update_mmu_cache_pmd(vma, addr, pmdp);
+ if (page_locked)
+ unlock_page(page);
+
+out_unlock:
+ spin_unlock(&mm->page_table_lock);
+ if (current_nid != -1)
+ task_numa_fault(current_nid, HPAGE_PMD_NR, migrated);
+ return 0;
+}
+
int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
pmd_t *pmd, unsigned long addr)
{
if (is_huge_zero_pmd(orig_pmd)) {
tlb->mm->nr_ptes--;
spin_unlock(&tlb->mm->page_table_lock);
+ put_huge_zero_page();
} else {
page = pmd_page(orig_pmd);
page_remove_rmap(page);
}
int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
- unsigned long addr, pgprot_t newprot)
+ unsigned long addr, pgprot_t newprot, int prot_numa)
{
struct mm_struct *mm = vma->vm_mm;
int ret = 0;
if (__pmd_trans_huge_lock(pmd, vma) == 1) {
pmd_t entry;
entry = pmdp_get_and_clear(mm, addr, pmd);
- entry = pmd_modify(entry, newprot);
- BUG_ON(pmd_write(entry));
+ if (!prot_numa) {
+ entry = pmd_modify(entry, newprot);
+ BUG_ON(pmd_write(entry));
+ } else {
+ struct page *page = pmd_page(*pmd);
+
+ /* only check non-shared pages */
+ if (page_mapcount(page) == 1 &&
+ !pmd_numa(*pmd)) {
+ entry = pmd_mknuma(entry);
+ }
+ }
set_pmd_at(mm, addr, pmd, entry);
spin_unlock(&vma->vm_mm->page_table_lock);
ret = 1;
* We can't temporarily set the pmd to null in order
* to split it, the pmd must remain marked huge at all
* times or the VM won't take the pmd_trans_huge paths
- * and it won't wait on the anon_vma->root->mutex to
+ * and it won't wait on the anon_vma->root->rwsem to
* serialize against split_huge_page*.
*/
pmdp_splitting_flush(vma, address, pmd);
page_tail->mapping = page->mapping;
page_tail->index = page->index + i;
+ page_xchg_last_nid(page_tail, page_last_nid(page));
BUG_ON(!PageAnon(page_tail));
BUG_ON(!PageUptodate(page_tail));
BUG_ON(page_mapcount(page) != 1);
if (!pmd_young(*pmd))
entry = pte_mkold(entry);
+ if (pmd_numa(*pmd))
+ entry = pte_mknuma(entry);
pte = pte_offset_map(&_pmd, haddr);
BUG_ON(!pte_none(*pte));
set_pte_at(mm, haddr, pte, entry);
return ret;
}
-/* must be called with anon_vma->root->mutex hold */
+/* must be called with anon_vma->root->rwsem held */
static void __split_huge_page(struct page *page,
struct anon_vma *anon_vma)
{
BUG_ON(is_huge_zero_pfn(page_to_pfn(page)));
BUG_ON(!PageAnon(page));
- anon_vma = page_lock_anon_vma(page);
+ anon_vma = page_lock_anon_vma_read(page);
if (!anon_vma)
goto out;
ret = 0;
BUG_ON(PageCompound(page));
out_unlock:
- page_unlock_anon_vma(anon_vma);
+ page_unlock_anon_vma_read(anon_vma);
out:
return ret;
}
if (pmd_trans_huge(*pmd))
goto out;
- anon_vma_lock(vma->anon_vma);
+ anon_vma_lock_write(vma->anon_vma);
pte = pte_offset_map(pmd, address);
ptl = pte_lockptr(mm, pmd);
}
smp_wmb(); /* make pte visible before pmd */
pmd_populate(mm, pmd, pgtable);
+ put_huge_zero_page();
}
void __split_huge_page_pmd(struct vm_area_struct *vma, unsigned long address,